The paper proves W[1]-hardness parameterized by dimension d for positivity, zonotope containment, max approximation, and L_p-Lipschitz constants in 2- and 3-layer ReLU networks, showing enumeration methods are optimal under ETH.
Efficient backward reachability using the minkowski difference of constrained zonotopes
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CC 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Parameterized Hardness of Zonotope Containment and Neural Network Verification
The paper proves W[1]-hardness parameterized by dimension d for positivity, zonotope containment, max approximation, and L_p-Lipschitz constants in 2- and 3-layer ReLU networks, showing enumeration methods are optimal under ETH.